AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks

Yuxin Sun, Dong Lao, Anthony Yezzi, Ganesh Sundaramoorthi

JMLR 2024 · Optimization › Implicit bias and generalization · approach: Edge-of-stability dynamics · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
perturb SGD update at the last floating point bit (k=3 to 11) (ablation)SGD · ResNet-56 CIFAR-10 ReLUfinal test accuracy STD: 0.11 -> 0.22Hurt
increase precision from 32 bit to 64 bitSGD · ResNet-56 CIFAR-10test accuracy STD: 0.16 -> 0.15No clear effect
replace ReLU with Swish activation (ablation)perturbed SGD · ResNet-56 CIFAR-10test accuracy STD under float perturbation: 0.16 -> 0.15No clear effect
switch SGD to Adam optimizer (ablation)perturbed SGD · ResNet-56 CIFAR-10 Swishtest accuracy STD: 0.22 -> 0.28No clear effect
use VGG16BN instead of ResNet56 and Fashion-MNIST instead of CIFAR-10 (ablation)perturbed SGD · Swishtest accuracy STD: 94.81 ± 0.09No clear effect
multiply k by a power of two (k=1 vs k=2,4) (ablation)perturbed SGD · ResNet-56 CIFAR-10final test accuracy: 93.47 -> 93.47No clear effect
decrease learning rate to a stable value 3.125e-6 (ablation)SGD · ResNet-56 CIFAR-10weight divergence between k=1 and k=3Improved
use 3-layer CNN instead of 1-layer CNN at learning rate 5 (ablation)gradient descent · single-datum CNNloss stabilityHurt
double the layers of a 2-layer FC network without weight decay (ablation)gradient descent · CIFAR-5kloss stabilityHurt
increase learning rate from 0.03 to 0.05 (ablation)gradient descent · 1-layer CNN single datumnormalized sharpnessHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy